Context object for this purpose.
FastMCP uses Docket’s dependency injection system for managing runtime dependencies. This page covers Context and the built-in dependencies; see Custom Dependencies for creating your own.
What Is Context?
TheContext object provides a clean interface to access MCP features within your functions, including:
- Logging: Send debug, info, warning, and error messages back to the client
- Progress Reporting: Update the client on the progress of long-running operations
- Resource Access: List and read data from resources registered with the server
- Prompt Access: List and retrieve prompts registered with the server
- LLM Sampling: Request the client’s LLM to generate text based on provided messages
- User Elicitation: Request structured input from users during tool execution
- State Management: Store and share data between middleware and the handler within a single request
- Request Information: Access metadata about the current request
- Server Access: When needed, access the underlying FastMCP server instance
Accessing the Context
New in version2.14
The preferred way to access context is using the CurrentContext() dependency:
- Dependency parameters are automatically excluded from the MCP schema—clients never see them.
- Context methods are async, so your function usually needs to be async as well.
- Each MCP request receives a new context object. Context is scoped to a single request; state or data set in one request will not be available in subsequent requests.
- Context is only available during a request; attempting to use context methods outside a request will raise errors.
Legacy Type-Hint Injection
For backwards compatibility, you can still access context by simply adding a parameter with theContext type hint. FastMCP will automatically inject the context instance:
Context type hint is important. The type hint can also be a union (Context | None) or use Annotated[].
Via get_context() Function
New in version 2.2.11
For code nested deeper within your function calls where passing context through parameters is inconvenient, use get_context() to retrieve the active context from anywhere within a request’s execution flow:
- The
get_context()function should only be used within the context of a server request. Calling it outside of a request will raise aRuntimeError. - The
get_context()function is server-only and should not be used in client code.
Context Capabilities
FastMCP provides several advanced capabilities through the context object. Each capability has dedicated documentation with comprehensive examples and best practices:Logging
Send debug, info, warning, and error messages back to the MCP client for visibility into function execution.Client Elicitation
New in version2.10.0
Request structured input from clients during tool execution, enabling interactive workflows and progressive disclosure. This is a new feature in the 6/18/2025 MCP spec.
LLM Sampling
New in version2.0.0
Request the client’s LLM to generate text based on provided messages, useful for leveraging AI capabilities within your tools.
Progress Reporting
Update clients on the progress of long-running operations, enabling progress indicators and better user experience.Resource Access
List and read data from resources registered with your FastMCP server, allowing access to files, configuration, or dynamic content.ctx.list_resources() -> list[MCPResource]: New in version2.13.0Returns list of all available resourcesctx.read_resource(uri: str | AnyUrl) -> list[ReadResourceContents]: Returns a list of resource content parts
Prompt Access
New in version2.13.0
List and retrieve prompts registered with your FastMCP server, allowing tools and middleware to discover and use available prompts programmatically.
ctx.list_prompts() -> list[MCPPrompt]: Returns list of all available promptsctx.get_prompt(name: str, arguments: dict[str, Any] | None = None) -> GetPromptResult: Get a specific prompt with optional arguments
State Management
New in version2.11.0
Store and share data between middleware and handlers within a single MCP request. Each MCP request (such as calling a tool, reading a resource, listing tools, or listing resources) receives its own context object with isolated state. Context state is particularly useful for passing information from middleware to your handlers.
To store a value in the context state, use ctx.set_state(key, value). To retrieve a value, use ctx.get_state(key).
This simplified example shows how to use MCP middleware to store user info in the context state, and how to access that state in a tool:
ctx.set_state(key: str, value: Any) -> None: Store a value in the context statectx.get_state(key: str) -> Any: Retrieve a value from the context state (returns None if not found)
- State set on a child context never affects the parent context
- State set on a parent context after the child context is initialized is not propagated to the child context
Change Notifications
New in version2.9.1
FastMCP automatically sends list change notifications when components (such as tools, resources, or prompts) are added, removed, enabled, or disabled. In rare cases where you need to manually trigger these notifications, you can use the context methods:
FastMCP Server
To access the underlying FastMCP server instance, you can use thectx.fastmcp property:
MCP Request
Access metadata about the current request and client.ctx.request_id -> str: Get the unique ID for the current MCP requestctx.client_id -> str | None: Get the ID of the client making the request, if provided during initializationctx.session_id -> str | None: Get the MCP session ID for session-based data sharing (HTTP transports only)
Request Context Availability
New in version2.13.1
The ctx.request_context property provides access to the underlying MCP request context, but returns None when the MCP session has not been established yet. This typically occurs:
- During middleware execution in the
on_requesthook before the MCP handshake completes - During the initialization phase of client connections
get_http_request() and get_http_headers().
Client Metadata
New in version2.13.1
Clients can send contextual information with their requests using the meta parameter. This metadata is accessible through ctx.request_context.meta and is available for all MCP operations (tools, resources, prompts).
The meta field is None when clients don’t provide metadata. When provided, metadata is accessible via attribute access (e.g., meta.user_id) rather than dictionary access. The structure of metadata is determined by the client making the request.
Runtime Dependencies
HTTP Requests
New in version2.2.11
The recommended way to access the current HTTP request is through the get_http_request() dependency function:
- You need access to HTTP information in helper functions
- You’re calling nested functions that need HTTP request data
- You’re working with middleware or other request processing code
HTTP Headers
New in version2.2.11
If you only need request headers and want to avoid potential errors, you can use the get_http_headers() helper:
get_http_headers() excludes problematic headers like host and content-length. To include all headers, use get_http_headers(include_all=True).
Access Tokens
New in version2.11.0
When using authentication with your FastMCP server, you can access the authenticated user’s access token information using the get_access_token() dependency function:
- Access user identification - Get the
client_idor subject from token claims - Check permissions - Verify scopes or custom claims before performing operations
- Multi-tenant applications - Extract tenant information from token claims
- Audit logging - Track which user performed which actions
Working with Token Claims
Theclaims field contains all the data from the original token (JWT claims for JWT tokens, or custom data for other token types):
Custom Dependencies
New in version2.14
FastMCP’s dependency injection is powered by Docket, which provides a flexible system for injecting values into your functions. Beyond the built-in dependencies like CurrentContext(), you can create your own.
Using Depends()
The simplest way to create a custom dependency is with Depends(). Pass any callable (sync or async function, or async context manager) and its return value will be injected:
Depends() are automatically excluded from the MCP schema—clients never see them as parameters.
Resource Management with Context Managers
For dependencies that need cleanup (database connections, file handles, etc.), use an async context manager:Nested Dependencies
Dependencies can depend on other dependencies:Advanced: Subclassing Dependency
For more complex dependency patterns—like dependencies that need access to Docket’s execution context or require custom lifecycle management—you can subclass Docket’s Dependency class. See the Docket documentation on dependencies for details.
